Non-linear Analysis Based ECG Classification of Cardiovascular Disorders

TL;DR

This paper introduces a non-linear analysis method using Recurrence plots for ECG classification, achieving 100% accuracy in distinguishing various cardiac disorders from healthy controls on a public dataset.

Contribution

The study presents a novel Recurrence plot-based approach for ECG classification that effectively captures non-linear features and improves disorder detection accuracy.

Findings

Achieved 100% classification accuracy on PTB dataset.

Recurrence plots reveal clear separation between disorders and healthy controls.

Latent space visualizations support the effectiveness of the method.

Abstract

Multi-channel ECG-based cardiac disorders detection has an impact on cardiac care and treatment. Limitations of existing methods included variation in ECG waveforms due to the location of electrodes, high non-linearity in the signal, and amplitude measurement in millivolts. The present study reports a non-linear analysis-based methodology that utilizes Recurrence plot visualization. The patterned occurrence of well-defined structures, such as the QRS complex, can be exploited effectively using Recurrence plots. This Recurrence-based method is applied to the publicly available Physikalisch-Technische Bundesanstalt (PTB) dataset from PhysioNet database, where we studied four classes of different cardiac disorders (Myocardial infarction, Bundle branch blocks, Cardiomyopathy, and Dysrhythmia) and healthy controls, achieving an impressive classification accuracy of 100%. Additionally, t-SNE plot visualizations of the latent space embeddings derived from Recurrence plots and Recurrence Quantification Analysis features reveal a clear demarcation between the considered cardiac disorders and healthy individuals, demonstrating the potential of this approach.